Daily work that cannot leave the laptop
Drafts, files, and context stay on this Mac. LOCAL by default.
ownership · today · Can I run private AI on a Mac instead of a $20–$200 chat seat?
Yes. TARX-OS runs locally on Apple silicon. Join the Supercomputer. First-run stays local. This is the Join path. LM Studio and Ollama are DIY chat windows. TARX-OS is the governed runtime on the same silicon. Get a T-4 when the desk needs dedicated NVIDIA.
LM Studio and Ollama are DIY chat windows. TARX-OS is the governed runtime on the same silicon.
TARX-LOCAL handles private work on your computer. Connections stay off until you allow them.
Human funnel: People →

People already have Macs. That is the first Supercomputer node they will ever Join. TARX-OS seats are $0. Local TARX-OS inference. LOCAL by default.
The product is not another chat window. Control waits on writes. Evidence records what ran. Vault holds secrets. You can stay on Macs only. Supercomputer is optional.
When the team outgrows the laptop, get a T-4 for indoor or vehicle work, indoor / vehicle. Same OS. Same approval. Same evidence.
TARX-OS on computers you already own. Supercomputer hardware when the site needs dedicated NVIDIA.
Drafts, files, and context stay on this Mac. LOCAL by default.
Same OS on every seat. No per-person license. Supercomputer only when shared work needs more.
Consequential actions wait on Deny or Allow once. Evidence after.
01
TARX-OS on a Mac you already own.
02
Nothing attaches until you opt in.
03
Writes wait. Evidence after.
04
Optional. Same runtime.
No. Start on Apple silicon you already own. Get a T-4 when the desk needs dedicated NVIDIA.
No. TARX-OS on Macs you already own is included. $0 seats.
Ollama is a local model runner. TARX-OS is the governed runtime: Spaces, Control, Evidence, Vault.
When the team outgrows the laptop and needs dedicated NVIDIA capacity on the desk.
Join the Supercomputer. Or own Private Hardware.
JOIN · TARX-OS

Always-on agents on silicon you own.
TARX is not a chat app. TARX-OS is the always-on governed runtime for AI agents and work. Install it on the Mac you already have. Chat is how you talk to it. The runtime stays on — goals, skills, approval, Evidence.
Join beta →OWN · TARX HARDWARE

When local is not enough, attach a TARX machine.
T-1, T-4, T-7, T-70, T-600. Model numbers. They join the Supercomputer — the mesh — for private cluster, burst, or air-gapped sites. Same OS. Same approval. Same Evidence.
Explore Private Hardware →TARX-OS seats are included. Configure the Supercomputer. Watch the math. Submit once.